LoRa trained on screencaps from various movies to create a less sanitized "plastic" style in flux. Use the generator keywords to roughly control the shot from close-up to wide.
Description
Cleaner and larger data set compared to version 1.0. See the example images for prompts. The images were trained with captions following the following structure:
cinematic <wide/full/medium/close-up> shot of <subject>. <Lighting>. <High/Medium/Low> resolution. <Decade> <movie>
FAQ
Details
Downloads
532
Platform
CivitAI
Platform Status
Available
Created
4/19/2025
Updated
5/14/2026
Deleted
-
Trigger Words:
close-up shot
medium shot
full shot
wide shut
cinematic
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.